OCRRouter

Unlimited OCR vs Chunkr

Pick Unlimited OCR to turn long reports and books into Markdown or text with bounding boxes in one pass, under an MIT licence. Pick Chunkr to parse PDFs, slides, Word files and images into semantic chunks for RAG, with a hosted API or a self-hosted Docker setup. The main split is scope: Unlimited OCR reads 40+ page documents in one forward pass, while Chunkr handles more input formats and returns HTML and JSON.

Unlimited OCRbaidu/unlimited-ocrChunkrchunkr/chunkr
TypeOpen sourceOCR API
Price2 credits / page14 credits / page
Per 1,000 pages$2.00$14.00
Typical speed1.2 s / page3.0 s / page
Best forBooks and very long documentsLayout-aware chunks for RAG
InputsPDF, imagesPDF, images, DOCX
Languages30+ languagesMultilingual
Max pages per request1,0001,000
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ Yes
On OCRRouterAvailableAvailable

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

Which to choose

Choose Unlimited OCR if

  • It parses 40+ pages in a single forward pass with roughly constant memory, so long reports and books go in as one request.
  • The MIT licence allows commercial use with no copyleft, so you can ship it in a closed product.
  • Baidu reports 77.1 on MarathonDocBench for Unlimited OCR 2, against 33.7 for the next model.

Choose Chunkr if

  • It accepts PDF, PPT, Word and images, and returns HTML, Markdown, JSON and bounding boxes.
  • It does semantic chunking, which suits RAG over PDFs and slides.
  • Self-hosting runs through Docker with GPU, CPU-only and Mac ARM options, and works with any OpenAI-compatible LLM endpoint.

Key differences

Unlimited OCRChunkr
LicenceMIT, commercial use allowed, no copyleftAGPL-3.0, or a commercial licence for closed use
How you run itSelf-host with vLLM, SGLang or transformers; hosted endpoint in Baidu Cloud's OCR productCloud API, or open-source self-host via Docker that needs an external LLM endpoint
PriceFree self-hosted, you pay for compute; hosted pricing not publishedHosted credit-based plans, official prices not verified; open-source version is free, you pay for compute and an LLM endpoint
Output formatsMarkdown, plain text, bounding boxesHTML, Markdown, JSON, bounding boxes
HardwareNVIDIA GPU with CUDA 12.9 or 13.0; version 2 under SGLang runs out of memory on 12 GB GPUs; no CPU-only useGPU, CPU-only and Mac ARM options
BenchmarksParseBench mean 46.17 (independent); MPDocBench 84.6 and MarathonDocBench 77.1 for version 2 (by the authors)Not published
Known failureText repetition and looping, hallucinated text, bbox coordinate loops under SGLang on GB10 GPUs, and bold or italic styling mostly lostOpen-source version uses community models that are less accurate than the cloud's, and Excel is not supported there

Sources

What each one is

Unlimited OCR

Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.

Unlimited OCR details

Chunkr

Document parsing API that segments and chunks pages for RAG. Self-hostable version available.

Chunkr details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

Use one, fall back to the other

{"model": "baidu/unlimited-ocr","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Unlimited OCR alternativesChunkr alternativesBest OCR models in 2026